Question Q1(A)

a) Hypotheses:

1. **Age and Customer Lifetime Value**: Older customers may have a higher customer lifetime value compared to
younger customers due to factors such as higher disposable income, established shopping habits, and brand
loyalty.

2. **Annual Income and Customer Lifetime Value**: Customers with higher annual incomes may exhibit a higher
customer lifetime value as they have more purchasing power and may be more willing to spend on premium
products or services offered by the retailer.

3. **Duration of Association and Customer Lifetime Value**: Customers who have been associated with the
retailer for a longer duration may have a higher customer lifetime value compared to newer customers, as they
have had more opportunities to make purchases and engage with the brand over time.

b) Analytical Methods:

1. **Regression Analysis**: Regression analysis can be used to model the relationship between customer
characteristics (age, annual income, duration of association) and customer lifetime value. By fitting a regression
model, we can quantify the impact of each predictor variable on customer lifetime value while controlling for other
factors.

Insights:
- Regression coefficients will indicate the strength and direction of the relationships between customer
characteristics and customer lifetime value.
- We can identify which customer characteristics are significant predictors of customer lifetime value and
prioritize marketing strategies targeting those segments. For example, if age and annual income are found to be
significant predictors, the retailer may focus on marketing campaigns tailored to older, higher-income
demographics.

2. **Cluster Analysis**: Cluster analysis can help segment customers based on their characteristics and behaviors,
allowing for a deeper understanding of different customer segments and their corresponding customer lifetime
values. By grouping customers with similar traits together, the retailer can identify high-value customer segments
and tailor marketing strategies accordingly.

Insights:
- Cluster analysis can reveal distinct customer segments with varying customer lifetime values, enabling the
retailer to prioritize resources and efforts on segments with the highest potential for long-term profitability.
- Insights gained from cluster analysis can inform personalized marketing strategies, loyalty programs, and
product offerings targeted at specific customer segments. For instance, if a cluster analysis reveals a segment of
high-income, long-term customers, the retailer can develop exclusive loyalty perks or premium product lines to
further incentivize their patronage.

By applying regression analysis and cluster analysis to the dataset, the online retailer can gain valuable insights into
the relationship between consumer characteristics and customer lifetime value, ultimately guiding the
development of effective marketing recommendations to enhance customer retention and maximize profitability.
 Question 1(B)

a) Identify the problem:

The problem identified is eve teasing, which refers to the harassment or molestation of women by men. It
encompasses a wide range of behaviors, from sexually colored remarks to outright assault. Eve teasing is described
as a form of enjoyment for men but as physical and mental torture for women. It severely impacts women's sense
of security, mobility, and overall well-being in public spaces. It perpetuates gender inequality and reinforces
women's subordinate social status in society.

b) Develop hypotheses:
1. Hypothesis 1: The prevalence of eve teasing is higher in regions where there is a greater gender disparity in
social norms, values, and expectations between men and women.
2. Hypothesis 2: Media portrayal of gender roles and violence against women contributes to the normalization and
perpetuation of eve teasing behavior in society.
3. Hypothesis 3: The lack of accountability and minimal sanctions for perpetrators of eve teasing, particularly men,
perpetuates a culture of impunity and encourages further incidents of harassment.

c) Develop an interview schedule:

1. Introduction:
- Explain the purpose of the interview: to understand perceptions and experiences related to eve teasing.
- Assure confidentiality and voluntary participation.
2. Demographic Information:
- Gender
- Age
- Occupation
- Location (urban/rural)
3. Perceptions of Eve Teasing:
- Have you ever witnessed or experienced eve teasing? Please describe the incident.
- How prevalent do you think eve teasing is in your community?
- What are the factors that contribute to eve teasing according to you?
4. Socialization and Gender Norms:
- How do you perceive the role of socialization and gender norms in shaping attitudes towards eve teasing?
- Do you think there is a disparity in the way boys and girls are socialized regarding acceptable behavior?
5. Media Influence:
- How do you think media portrayal of gender roles and violence against women influences attitudes towards eve
teasing?
- Have you ever observed instances in media where eve teasing behavior was normalized or justified?
6. Accountability and Sanctions:
- What are your thoughts on the accountability of perpetrators of eve teasing?
- Do you believe there are sufficient consequences for individuals who engage in eve teasing?
7. Impact on Women:
- How do you think eve teasing affects women's sense of security and mobility in public spaces?
- Have you observed any changes in women's behavior or actions due to fear of eve teasing?
8. Suggestions for Addressing Eve Teasing:
- What measures do you think can be taken to prevent eve teasing and support victims?
- How can communities and institutions work together to create safer environments for women?

The interview schedule aims to gather insights into the perceptions, experiences, and underlying factors related to
eve teasing, which can inform strategies for addressing this pervasive issue in Indian society.
 Question 2(A)

a) Likert Scale:
To compare HP and Apple laptops on the attributes of speed of processor and value for money, a Likert scale can
be designed as follows:

1. Speed of Processor:
- Very Slow
- Slow
- Neutral
- Fast
- Very Fast

2. Value for Money:

- Poor Value
- Below Average Value
- Neutral
- Above Average Value
- Excellent Value

Participants would be asked to rate each attribute for both HP and Apple laptops using the Likert scale, indicating
their perception of the speed of the processor and the value for money offered by each brand.

b) Semantic Differential Scale:

For the semantic differential scale, pairs of opposite adjectives are used to assess the attributes of HP and Apple
laptops:

1. Speed of Processor:
- Very Slow ◊◊◊◊◊ Very Fast

2. Value for Money:

- Poor Value ◊◊◊◊◊ Excellent Value

Participants would be asked to mark their perception of each laptop brand's speed of processor and value for
money along the continuum between the opposite adjectives. The closer the mark to one end of the scale, the
stronger the perception of that attribute for the respective laptop brand.
 Question 4

Factor analysis is a statistical technique used to identify patterns in data and reduce the number of variables to a
smaller set of underlying factors. In the context of consumer preferences for a shopping mall, factor analysis can
help understand which features or aspects of the mall are most important to consumers.

Here are the steps typically involved in conducting factor analysis:

1. **Define the Objective**: Determine the purpose of the analysis and the variables (features) to include. In this
case, variables might include features of the shopping mall like parking, escalator, security, lighting, entertainment
zone, kids zone, food court, and weekly events.

2. **Data Collection**: Gather data on consumer preferences, often through surveys or other forms of data
collection.

3. **Data Preprocessing**: Clean the data to handle missing values, outliers, and other issues that may affect the
analysis.

4. **Factor Extraction**: Use techniques such as principal component analysis (PCA) or common factor analysis to
extract the underlying factors from the data. This step aims to identify the smallest number of factors that explain
the most variance in the data.

5. **Factor Rotation**: Rotate the factors to make them easier to interpret and interpret the relationships
between variables and factors. Common rotation methods include Varimax, Promax, and Quartimax.

6. **Interpretation**: Interpret the rotated factor matrix to understand the relationships between variables and
factors.

Now, let's interpret the rotated component matrix provided:

- **Component 1**: This component seems to represent factors related to amenities and leisure facilities in the
shopping mall. Variables such as entertainment zone, kids zone, food court, and weekly events have high loadings
on this component. This suggests that consumers who prefer amenities and leisure activities are likely to value
these features in a shopping mall.

- **Component 2**: This component appears to represent factors related to convenience and accessibility.
Variables like parking, escalator, security, and to some extent lighting, have high loadings on this component. This
indicates that consumers who prioritize convenience and safety are likely to value these features in a shopping
mall.

In summary, based on this interpretation, it seems that consumers' preferences for a shopping mall can be largely
categorized into two main factors: amenities/leisure facilities and convenience/accessibility. These factors can help
mall developers and managers understand what aspects of the mall are most important to their target consumers
and tailor their offerings accordingly.
 Question 4

Factor analysis is a statistical method used to identify underlying relationships between variables. In the context of
consumer preferences for a shopping mall, factor analysis can help identify the key factors that influence consumer
satisfaction or preferences.

Here are the steps involved in conducting factor analysis:

1. **Data Collection**: Gather data on consumer preferences for the shopping mall. This could include survey
responses or other relevant data sources.

2. **Data Preparation**: Clean the data and ensure it meets the assumptions of factor analysis, such as having
continuous variables and a sufficiently large sample size.

3. **Factor Extraction**: Use a factor extraction method, such as principal component analysis (PCA) or common
factor analysis, to identify the underlying factors that explain the correlations between observed variables. This
step aims to reduce the dimensionality of the data while retaining as much information as possible.

4. **Factor Rotation**: If necessary, rotate the factors to achieve a simpler and more interpretable factor
structure. Common rotation methods include varimax, promax, and oblimin rotation. Rotated factor loadings
indicate the strength and direction of the relationship between variables and factors.

5. **Interpretation**: Interpret the rotated factor matrix to understand the underlying factors and their
relationship with the observed variables. Factors with high loadings (absolute values closer to 1) indicate a strong
relationship with the variables.

Now, let's interpret the rotated component matrix provided in the context of consumer preferences for a shopping
mall:

- **Component 1**: This component seems to be primarily associated with amenities and features related to
convenience and practicality. Variables such as Parking (.146), Security (.238), and Escalator (-.079) have moderate
to high loadings on this component. This suggests that consumers who prefer convenient parking, security
measures, and easy access via escalators may be more likely to favor this component.

- **Component 2**: This component appears to be associated with amenities and features related to leisure and
entertainment. Variables such as Entertainment Zone (.877), Kids Zone (.771), and Food Court (.770) have high
loadings on this component. This suggests that consumers who value entertainment options, facilities for children,
and a diverse food court experience may be more inclined towards this component.

It's important to note that the interpretation of factors should be based on theoretical considerations and domain
knowledge in addition to the statistical results. Additionally, further analyses or validation steps may be needed to
confirm the stability and validity of the identified factors.